Classifier_Bayes: Classifier based on Bayes rule

In EMMIXSSL: Semi-Supervised Gaussian Mixture Model with a Missing-Data Mechanism

Classifier based on Bayes rule

Description

A classifier based on Bayes rule, that is maximum a posterior probabilities of class membership

Usage

Classifier_Bayes(dat, n, p, g, pi, mu, sigma, ncov = 2)

Arguments

dat	An n\times p matrix where each row represents an individual observation
n	Number of observations.
p	Dimension of observation vecor.
g	Number of classes.
pi	A g-dimensional vector for the initial values of the mixing proportions.
mu	A p \times g matrix for the initial values of the location parameters.
sigma	A p\times p covariance matrix if ncov=1, or a list of g covariance matrices with dimension p\times p \times g if ncov=2.
ncov	Options of structure of sigma matrix; the default value is 2; ncov = 1 for a common covariance matrix; ncov = 2 for the unequal covariance/scale matrices.

Details

The posterior probability can be expressed as

τ_i(y_j;θ)=Prob\{z_{ij}=1|y_j\}=\frac{π_iφ(y_j;μ_i,Σ_i)}{∑_{h=1}^gπ_hφ(y_j;μ_h,Σ_h) },

where φ is a normal probability function with mean μ_i and covariance matrix Σ_i, and z_{ij} is is a zero-one indicator variable denoting the class of origin. The Bayes' Classifier of allocation assigns an entity with feature vector y_j to Class C_k if

k= arg max_i τ_i(y_j;θ).

Value

cluster

A vector of the class membership.

Examples

n<-150
pi<-c(0.25,0.25,0.25,0.25)
sigma<-array(0,dim=c(3,3,4))
sigma[,,1]<-diag(1,3)
sigma[,,2]<-diag(2,3)
sigma[,,3]<-diag(3,3)
sigma[,,4]<-diag(4,3)
mu<-matrix(c(0.2,0.3,0.4,0.2,0.7,0.6,0.1,0.7,1.6,0.2,1.7,0.6),3,4)
dat<-rmix(n=n,pi=pi,mu=mu,sigma=sigma,ncov=2)
cluster<-Classifier_Bayes(dat=dat$Y,n=150,p=3,g=4,mu=mu,sigma=sigma,pi=pi,ncov=2)

EMMIXSSL documentation built on Oct. 18, 2022, 5:08 p.m.